© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64450
    Prev
    Next
    INDEX
    Explanations

    MotionEvent ACTION types

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects Android input‐event code, especially references to MotionEvent action constants.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Callaway
    -0.85
     desar
    -0.81
     gobern
    -0.73
     derra
    -0.71
    buka
    -0.70
    tellbar
    -0.69
     растение
    -0.69
    inawa
    -0.68
     đánh
    -0.68
    hehehe
    -0.68
    POSITIVE LOGITS
     pointer
    0.96
    Action
    0.93
     action
    0.90
    ACTION
    0.88
    Masked
    0.87
    action
    0.86
    pointer
    0.83
     Action
    0.82
     pointers
    0.81
    getAction
    0.79
    Activations Density 0.004%

    No Known Activations